df <- read.csv2('https://raw.githubusercontent.com/mcasky16/RR_Final_Project/main/student_feedback.csv', sep = ',')
COLUMN NAMES names(df) ## [1] “X”
## [2] “Student.ID”
## [3] “Well.versed.with.the.subject”
## [4] “Explains.concepts.in.an.understandable.way”
## [5] “Use.of.presentations”
## [6] “Degree.of.difficulty.of.assignments”
## [7] “Solves.doubts.willingly”
## [8] “Structuring.of.the.course”
## [9] “Provides.support.for.students.going.above.and.beyond” ## [10]
“Course.recommendation.based.on.relevance”
POTENTIAL QUESTIONS TO BE ANSWERED How is “course recommendation based on relevance distributed” as density plot?
Average use of presentation
CORRELATION between solves doubt AND explain concept in an understandable way
Bar chart student well versed with the topic
on the scale to one to 10 how much difficult assignment is 6- scale and 7-scale
Bar chart rating for teacher that Solves doubt willingly
REMOVING MISSING VALUES TO CLEAN THE DATA AND AVOID ERRORS df_nona implies df with no null values
df_nona = df%>%drop_na()
How is “course recommendation based on relevance distributed” as density plot?
## Warning: Ignoring unknown parameters: bins
##
Average use of presentation
df_nona %>%
summarize(average_use_ofpresentation= round(mean(Use.of.presentations)))
## average_use_ofpresentation
## 1 6
on the scale of 1-10 average ratimg that student feel that they will use presentation for topic is 6
on the scale to one to 10 ho much difficult assignment is 6- scale and 7-scale
df_nona %>%
filter(Degree.of.difficulty.of.assignments %in% c('6', '7'))%>%
ggplot() +
geom_density(aes(x = Degree.of.difficulty.of.assignments , fill = Degree.of.difficulty.of.assignments , alpha = 0.1))+
labs(title = 'Degree.of.difficulty.of.assignments',
subtitle= 'Mumbai student survey' , x= 'Degree.of.difficulty.of.assignments',y= 'Frequency') +
ggthemes::theme_stata()
df_nona %>%
group_by(Well.versed.with.the.subject)%>%
count(sort =TRUE) %>%
head(10)%>%
ggplot() +
geom_col(aes(x= reorder(Well.versed.with.the.subject , n) , y = n), fill = "Pink") +
geom_label(aes(x= reorder(Well.versed.with.the.subject , n) , y = n , label=n))+
coord_flip() +
labs(title = 'no. of student who are well versed ',
x= 'scale',y= 'Frequency')+
ggthemes::theme_economist_white()-> scale....
plotly:: ggplotly(scale....)
df_nona %>%
group_by(Solves.doubts.willingly)%>%
count(sort =TRUE)%>%
ggplot() +
geom_col(aes(x= reorder(Solves.doubts.willingly, n) , y = n), fill = "purple" ) +
geom_label(aes(x= reorder(Solves.doubts.willingly , n) , y = n , label=n))+
ggthemes::theme_gdocs()->gg....Solves.doubts.willingly
plotly:: ggplotly(gg....Solves.doubts.willingly)
df_nona%>%
select(c('Solves.doubts.willingly' ,'Explains.concepts.in.an.understandable.way')) %>%
cor()
## Solves.doubts.willingly
## Solves.doubts.willingly 1.00000000
## Explains.concepts.in.an.understandable.way -0.02583881
## Explains.concepts.in.an.understandable.way
## Solves.doubts.willingly -0.02583881
## Explains.concepts.in.an.understandable.way 1.00000000
correlation less than 0 indicate a negative correlation in our case it is -0.0258
Since the points or values are range in absolute integer the scatter plot is not showing good result
df_nona%>%
select(c('Solves.doubts.willingly' ,'Explains.concepts.in.an.understandable.way')) %>%
ggplot(aes(x= Solves.doubts.willingly , y = Explains.concepts.in.an.understandable.way))+
geom_point(color = "#6c094f")+
geom_smooth(method = lm)+
labs(title = "correlation Scatter Plot" )